Multi-Layer Perceptron-Based Relay Node Selection for Next-Generation Intelligent Delay-Tolerant Networks

Abstract

Delay Tolerant Networks (DTNs) are critical for emergency communication in highly dynamic and challenging scenarios characterized by intermittent connectivity, frequent disruptions, and unpredictable node mobility. While some protocols are widely adopted for simplicity and low overhead, their static replication strategy lacks the ability to adaptively distinguish high-quality relay nodes, often leading to inefficient and suboptimal message dissemination. To address this challenge, we propose a novel intelligent routing enhancement that integrates machine learning-based node evaluation into the Spray and Wait framework. Several dynamic, core features are extracted from simulation logs and are used to train multiple classifiers - Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), and Random Forest (RF) - to predict whether a node is suitable as a relay under dynamic conditions. The trained models are deployed via a lightweight Flask-based RESTful API, enabling real-time, adaptive predictions. We implement the enhanced router MLPBasedSprayRouter, which selectively forwards messages based on the predicted relay quality. A caching mechanism is incorporated to reduce computational overhead and ensure stable, low-latency inference. Extensive experiments under realistic emergency mobility scenarios demonstrate that the proposed framework significantly improves delivery ratio while reducing average latency compared to the baseline protocols. Among all evaluated classifiers, MLP achieved the most robust performance, consistently outperforming both SVM and RF in terms of accuracy, adaptability, and inference speed. These results confirm the novelty and practicality of integrating machine learning into DTN routing, paving the way for resilient and intelligent communication systems in smart cities, disaster recovery, and other dynamic environments.